Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2861 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.3491. Min Act: -0.0000

Data Index: 594686 (The Pile)

Max Activating Token Index: 912

Text #1

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.6345. Min Act: -0.0000

Data Index: 1568661 (The Pile)

Max Activating Token Index: 237

Text #2

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.4203. Min Act: -0.0000

Data Index: 552051 (The Pile)

Max Activating Token Index: 585

Text #3

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.5850. Min Act: -0.0000

Data Index: 1862400 (The Pile)

Max Activating Token Index: 679

Text #4

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.4607. Min Act: -0.0000

Data Index: 982124 (The Pile)

Max Activating Token Index: 319

Text #5

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.3643. Min Act: -0.0000

Data Index: 550031 (The Pile)

Max Activating Token Index: 783

Text #6

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.1988. Min Act: -0.0000

Data Index: 1449288 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.1842. Min Act: -0.0000

Data Index: 1743856 (The Pile)

Max Activating Token Index: 786

Text #8

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.2820. Min Act: -0.0000

Data Index: 1486139 (The Pile)

Max Activating Token Index: 128

Text #9

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.3032. Min Act: -0.0000

Data Index: 986973 (The Pile)

Max Activating Token Index: 607

Text #10

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.3109. Min Act: -0.0000

Data Index: 750322 (The Pile)

Max Activating Token Index: 902

Text #11

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.2900. Min Act: -0.0000

Data Index: 1003669 (The Pile)

Max Activating Token Index: 65

Text #12

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.3807. Min Act: -0.0000

Data Index: 379036 (The Pile)

Max Activating Token Index: 77

Text #13

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.2803. Min Act: -0.0000

Data Index: 281358 (The Pile)

Max Activating Token Index: 869

Text #14

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.1739. Min Act: -0.0000

Data Index: 1968916 (The Pile)

Max Activating Token Index: 519

Text #15

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.2891. Min Act: -0.0000

Data Index: 564958 (The Pile)

Max Activating Token Index: 577

Text #16

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.2451. Min Act: -0.0000

Data Index: 1213210 (The Pile)

Max Activating Token Index: 807

Text #17

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.1385. Min Act: -0.0000

Data Index: 1205315 (The Pile)

Max Activating Token Index: 125

Text #18

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.0799. Min Act: -0.0000

Data Index: 176410 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.1124. Min Act: -0.0000

Data Index: 742350 (The Pile)

Max Activating Token Index: 612